lemma_create_external_account

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full disclosure burden, and it does so well: it clearly warns that the tool 'Creates a REAL payment destination' and that saved recipients are 'IMMUTABLE once created'. It also discloses the absence of an update API and the manual email-based archiving path, so an agent understands the operation is permanent and not reversible through normal API calls.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but well-structured: it front-loads the action and then immediately surfaces the highest-risk warnings. Every sentence earns its place, especially the immutability, no-update-API, email-archiving, and double-check guidance. There is no filler or redundant boilerplate.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is strong on behavioral warnings and workflow placement, but it never states what the successful call returns—for example, an external account ID to be used with lemma_move_money_externally. Since there is no output schema, this return-value gap is meaningful. It also leaves some parameter semantics to the schema, which only partially covers them, so the overall context is not fully complete for an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already covers key parameter semantics such as the confirm approval gate, reference idempotency, routing number format, and holder address constraints. The description adds the actionable warning to 'double-check routing/account numbers before confirming', but it does not explain the meaning or format of entity_id, account_number, nickname, or holder_type. With schema description coverage at 56%, the description compensates only partially and relies mostly on the schema and required fields.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description starts with 'save a new external bank account (saved recipient) for an entity', which is a specific verb and resource that clearly differentiates this creation tool from the sibling get/list tools. It also positions it as the 'required first step before any external transfer', reinforcing its place in the workflow. There is no ambiguity with lemma_create_card or lemma_move_money_externally.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly tells the agent when to use this tool: before any external transfer, as the required first step. It also warns that there is no update API and that archiving must be done by emailing the Lemma team, which effectively tells the agent what not to expect from or attempt via the API. However, it does not explicitly name alternatives for inspecting existing recipients, such as lemma_list_external_accounts.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.